Abstract

Multimodal Sentiment Analysis is an active area of research that leverages multimodal signals for affective understanding of user-generated videos. The predominant approach, addressing this task, has been to develop sophisticated fusion techniques. However, the heterogeneous nature of the signals creates distributional modality gaps that pose significant challenges. In this paper, we aim to learn effective modality representations to aid the process of fusion. We propose a novel framework, MISA, which projects each modality to two distinct subspaces. The first subspace is modality-invariant, where the representations across modalities learn their commonalities and reduce the modality gap. The second subspace…

Citation impact

865
total citations
FWCI
54.85
Percentile
100%
References
46
Citations per year

Authors

3

Topics & keywords

Keywords
  • Modality (human–computer interaction)
  • Computer science
  • Modalities
  • Linear subspace
  • Task (project management)
  • Artificial intelligence
  • Subspace topology
  • Process (computing)
No related works found for this paper.

Funding